© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 57729
    Prev
    Next
    INDEX
    Explanations

    a copy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yyy
    -0.09
    eday
    -0.09
     either
    -0.09
    hos
    -0.09
     no
    -0.08
    atham
    -0.08
     */č↵č↵č↵
    -0.08
    ymm
    -0.08
    ecute
    -0.08
    yyyy
    -0.08
    POSITIVE LOGITS
    gov
    0.08
     Lub
    0.08
    uber
    0.08
    aged
    0.08
    lus
    0.08
     ratt
    0.08
     centerpiece
    0.08
     Scot
    0.08
    reste
    0.08
    SCO
    0.08
    Activations Density 0.033%

    No Known Activations